Teacher course quality evaluation system and method based on data analysis

Abstract

The invention relates to the technical field of teaching content evaluation, and discloses a teacher course quality evaluation system and method based on data analysis, and the system comprises a playing data collection end which is used for collecting historical playing data of a teaching video; the content extractor is used for performing content analysis on the video content according to the historical playing data, extracting the video according to a content analysis result, and obtaining extracted content; the evaluation module is used for acquiring evaluation information of the extracted content and evaluation information of the whole teaching video in real time; the user score analysis module is used for analyzing the scores of the users to obtain a teaching effect value of each teaching video; and the quality evaluation module is used for evaluating the teaching quality according to the historical playing data of the teaching video, the evaluation information of the extracted content, the evaluation information of the whole teaching video and the teaching effect value. Key content in teaching video content is extracted through the content extractor, and accurate acquisition of online class evaluation data of teachers is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of teaching content evaluation, and in particular to a teacher course quality evaluation system and method based on data analysis. Background Art

[0002] With the vigorous development of online education, the method of assisting learning through the Internet is becoming more and more popular among users. Teachers can widely disseminate high-quality educational resources by publishing teaching videos on teaching platforms. When students have problems or difficulties in their studies, they can supplement the lack of knowledge through the Internet. The evaluation of the quality of teachers' online teaching plays an important role in both the selection of teaching platform recommendations and the management of teacher resources on the teaching platform. Therefore, education platforms will evaluate the quality of teachers' online courses in various ways.

[0003] The existing teacher course quality evaluation methods mainly conduct comprehensive analysis through user active evaluation, video data analysis and user's overall performance. Among them, the process of user active evaluation mainly obtains user evaluation information by popping up an evaluation window to the user at the end of a teaching video, thereby realizing the evaluation of the quality of the teaching video. The video data is mainly judged by the number of video views. This method can judge the popularity of the teaching video and the user's feelings, thereby realizing the evaluation process of the teacher's course quality.

[0004] Although the existing teacher online course quality evaluation system can judge the quality of online courses, its evaluation accuracy is insufficient. Among them, the user's active evaluation process is a judgment on the entire teaching video, and the accurate evaluation of its content is insufficient. The video data and the user's overall performance are affected by many factors. Therefore, the existing teacher course quality evaluation system has the problem of insufficient judgment and deviation in result preparation. Therefore, how to improve the accuracy of teacher course quality evaluation is the fundamental problem to be solved by the present invention. Summary of the invention

[0005] In order to improve the accuracy of teacher course quality assessment, the present application provides a teacher course quality assessment system and method based on data analysis.

[0006] In the first aspect, the present application provides a teacher course quality evaluation system based on data analysis, which adopts the following technical solutions:

[0007] A teacher course quality evaluation system based on data analysis, including:

[0008] Playback data collection terminal, used to collect historical playback data of teaching videos;

[0009] A content extractor, used to perform content analysis on the video content according to the historical playback data, extract the video according to the content analysis result, and obtain the extracted content;

[0010] An evaluation module, used to obtain evaluation information of the extracted content and the entire teaching video in real time;

[0011] User performance analysis module, used to analyze the user's performance and obtain the teaching effect value of each teaching video;

[0012] The quality assessment module is used to evaluate the teaching quality based on the historical playback data of the teaching video, the evaluation information of the extracted content, the evaluation information of the entire teaching video and the teaching effect value.

[0013] By adopting the above technical solution, the content extractor is used to extract the key content in the teaching video content. At the same time, by separately obtaining the evaluation information of the extracted content, on the one hand, it is convenient to understand the user's knowledge point learning level in the management process of the education platform, and on the other hand, it is possible to accurately obtain the evaluation data of the teacher's online course, thereby improving the accuracy of the teacher's course quality evaluation in the subsequent judgment process; in addition, the playback data acquisition end in this system is connected to the relevant playback data acquisition of the teaching video background, and when the evaluation module obtains the evaluation information, it will not only collect the evaluation information of the entire teaching video, but also obtain the evaluation information of the extracted content in real time after each extracted content is completed. Due to the addition of the evaluation information of the extracted content, the accuracy of the teacher's course quality evaluation can be effectively improved.

[0014] Optionally, the process of the content extractor performing content analysis on the video content includes:

[0015] Divide the video content according to fixed preset unit time periods to obtain unit segments of each video;

[0016] Obtain the pause time point, playback rate change curve over time and video heat curve in the historical playback data of each unit segment;

[0017] The key value of each unit segment is calculated based on the historical playback data, and the extracted content is obtained based on the size of the key value.

[0018] By adopting the above technical solution, it is possible to accurately extract the key content in the teaching video based on the hot video content that users are paying attention to and the relevant operation data of the users in watching the teaching video (pause time points, playback rate change curve over time). The accuracy of the extracted content can facilitate the teaching platform to manage the teaching content on the one hand, and on the other hand, it can also evaluate the quality of teachers' courses more comprehensively by obtaining evaluations separately.

[0019] Optionally, the calculation process of the key value includes:

[0020] By formula:

[0021]

[0022] Calculate and obtain the key value Kv;

[0023] in, The starting time point for each unit segment, is the end time point of each unit segment, h(t) is the video heat curve, is the average heat value of the video, The interval length of each unit segment, m is the number of segments of the playback rate versus time curve within each unit segment, j=1, 2, …, m; is the playback rate of the jth segment, is the duration of the jth segment, is the first tuning coefficient, is the second tuning parameter, and n is the number of pause time points in each unit segment.

[0024] By adopting the above technical solution, the key values ​​obtained can be dynamically adjusted based on the user's attention and the user's inadvertent usage habits. For example, when the user is watching content that he considers important, the playback speed will be reduced or paused, thereby being able to more comprehensively integrate the data during the user's use and thus improve the accuracy of the extracted content.

[0025] Optionally, the process of obtaining the extracted content according to the size of the key value includes:

[0026] The key value Kv of each unit segment is compared with the preset fixed value K0, and the unit segment corresponding to the key value Kv>K0 is obtained as the extraction segment, and the adjacent extraction segments are merged as the extraction content.

[0027] By adopting the above technical solution, it is possible to segment and extract important parts of the teaching video according to the size of the key value, thereby facilitating the subsequent management of the teaching video and the individual evaluation process of each extracted content, thereby improving the accuracy of the quality assessment module in evaluating the teaching quality.

[0028] Optionally, the process of analyzing the user's performance by the user performance analysis module includes:

[0029] Get the user's score at each node and plot the score of each node into a score change curve;

[0030] The user's initial scores are divided into segments, and the user's teaching effect value is obtained according to the deviation state of the user's score change curve in each segment relative to the overall score change curve;

[0031] A teaching effect value is assigned to each teaching video according to the user's historical teaching video viewing data to obtain the teaching effect value assigned to each teaching video.

[0032] By adopting the above technical solution, the user is segmented according to his / her initial score, and the user teaching effect value is obtained according to the deviation state of the user score change curve in each segment relative to the overall score change curve, thereby achieving accurate evaluation of the user's score change. The quality of online course teaching is evaluated by obtaining the user's teaching effect value. In this process, the teaching effect value is allocated to each teaching video according to the user's historical teaching video viewing data, and the teaching effect value allocated to each teaching video is obtained, thereby realizing this process.

[0033] Optionally, the process of calculating the user teaching effect value includes:

[0034] By formula:

[0035]

[0036] Calculate and obtain the user teaching effect value E;

[0037] in, is the influence coefficient corresponding to the segment where the user's initial score is located, k is the k value of the user's score change curve, is the mean k value of all users’ performance change curves.

[0038] By adopting the above technical solution, through the formula The calculation process can judge the teaching results of a single user by obtaining the user teaching effect value E.

[0039] Optionally, the process of obtaining the teaching effect value of each teaching video includes:

[0040] By formula:

[0041]

[0042] Calculate the teaching effect value of each teaching video ;

[0043] Among them, Q is the number of users who watch each teaching video, y=1, 2, …, Q, is the teaching effect value of the yth user, The total viewing time of the user in this teaching video. The total viewing time of the user for the corresponding type of videos in this teaching video.

[0044] By adopting the above technical solution, the teaching effect value can be adjusted according to the different time users spend in the same type of teaching videos. By making reasonable allocation, the teaching effect of each teaching video can be matched one-to-one with each user, which improves the accuracy of the teaching effect value in judging the teaching quality.

[0045] In the second aspect, the present application provides a method for evaluating the quality of teacher courses based on data analysis, which adopts the following technical solutions:

[0046] A teacher course quality evaluation method based on data analysis includes: collecting historical playback data of teaching videos through a playback data collection terminal;

[0047] The evaluation module obtains the evaluation information of the extracted content and the evaluation information of the entire teaching video in real time;

[0048] Analyze the user's performance through the user performance analysis module to obtain the teaching effect value of each teaching video;

[0049] The teaching quality is evaluated through the quality assessment module based on the historical playback data of the teaching video, the evaluation information of the extracted content, the evaluation information of the entire teaching video and the teaching effect value.

[0050] By adopting the above technical solution, the content extractor is used to extract the key content in the teaching video content. At the same time, by separately obtaining the evaluation information of the extracted content, on the one hand, it is convenient to understand the user's knowledge point learning level in the management process of the education platform, and on the other hand, it is possible to accurately obtain the evaluation data of the teacher's online course, thereby improving the accuracy of the teacher's course quality evaluation in the subsequent judgment process; in addition, the playback data acquisition end in this system is connected to the relevant playback data acquisition of the teaching video background, and when the evaluation module obtains the evaluation information, it will not only collect the evaluation information of the entire teaching video, but also obtain the evaluation information of the extracted content in real time after each extracted content is completed. Due to the addition of the evaluation information of the extracted content, the accuracy of the teacher's course quality evaluation can be effectively improved.

[0051] In summary, the present application includes at least one of the following beneficial technical effects:

[0052] 1. The present invention realizes the extraction of key content in teaching video content through content extractor, and at the same time, by separately obtaining the evaluation information of the extracted content, on the one hand, it is convenient to understand the user's knowledge point learning degree in the management process of the education platform, and on the other hand, it realizes the accurate acquisition of the teacher's online course evaluation data, and then in the subsequent judgment process, improves the accuracy of the teacher's course quality evaluation; wherein, according to the user's attention to the hot video content and the user's viewing of the teaching video related operation data (pause time point, playback rate over time curve), it can accurately extract the key content in the teaching video, and the accuracy of the extracted content can facilitate the teaching platform to manage the teaching content on the one hand, and on the other hand, it can also evaluate the teacher's course quality more comprehensively by obtaining the evaluation separately. In addition, the playback data acquisition end in this system is connected to the relevant playback data acquisition of the teaching video background, and the evaluation module will not only collect the evaluation information of the entire teaching video when obtaining the evaluation information, but also obtain the evaluation information of the extracted content in real time after each extraction content is completed, and due to the addition of the evaluation information of the extracted content, it can effectively improve the accuracy of the teacher's course quality evaluation.

[0053] Second, the present invention divides the user into segments according to the initial score of the user, obtains the user teaching effect value according to the deviation state of the user score change curve under each segment relative to the overall score change curve, and thus realizes accurate evaluation of the user score change, that is, the online course teaching quality is evaluated by obtaining the user teaching effect value. In this process, the teaching effect value is allocated to each teaching video according to the user's historical teaching video viewing data, and the teaching effect value allocated to each teaching video is obtained, thereby realizing this process, and the formula is used. The calculation process can judge the teaching results of a single user through the obtained user teaching effect value E; at the same time, the teaching effect value can be evaluated according to the different occupancy time of users in the same type of teaching videos. By making reasonable allocation, the teaching effect of each teaching video can be matched one-to-one with each user, which improves the accuracy of the teaching effect value in judging the teaching quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a logical block diagram of the teacher course quality evaluation system based on data analysis;

[0055] Figure 2 It is a flowchart of the steps of the teacher course quality assessment method based on data analysis. DETAILED DESCRIPTION

[0056] Embodiments of the present application are described in detail below, examples of which are shown in the accompanying drawings.

[0057] In the description of this specification, the description with reference to the terms "certain embodiments", "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiments or examples are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0058] The present application embodiment discloses a teacher course quality evaluation system based on data analysis, referring to the attached Figure 1 , including a playback data collection end, a content extractor, an evaluation module, a user performance analysis module and a quality assessment module, wherein the playback data collection end is used to collect historical playback data of teaching videos, the content extractor is used to perform content analysis on the video content according to the historical playback data, extract the video according to the content analysis result, and obtain the extracted content, the evaluation module is used to obtain the evaluation information of the extracted content and the evaluation information of the entire teaching video in real time, the user performance analysis module is used to analyze the user's performance and obtain the teaching effect value of each teaching video, and finally the teaching quality is evaluated by the quality assessment module according to the historical playback data of the teaching video, the evaluation information of the extracted content, the evaluation information of the entire teaching video and the teaching effect value; compared with the teacher online course evaluation system in the prior art, the quality assessment method in the present application realizes the extraction of key content in the teaching video content by setting a content extractor, and at the same time, by separately obtaining the evaluation information of the extracted content, on the one hand, it is convenient to evaluate the user in the management process of the education platform On the one hand, it can help users understand the degree of learning of knowledge points, and on the other hand, it can realize the accurate acquisition of teacher online course evaluation data, so as to improve the accuracy of teacher course quality evaluation in the subsequent judgment process; in addition, the playback data acquisition end in this system is connected to the relevant playback data acquisition of the teaching video background, and when the evaluation module obtains the evaluation information, it will not only collect the evaluation information of the entire teaching video, but also obtain the evaluation information of the extracted content in real time after each extracted content is completed. This process can be achieved by placing a selection tag above the video, or by placing it in the tag bar below the video, without restriction here. Finally, the teaching quality is evaluated through the quality evaluation module. This process can be adjusted according to the focus of the education platform through weighted dynamic adjustment. The different weights of the historical playback data of the teaching video, the evaluation information of the extracted content, the evaluation information of the entire teaching video and the teaching effect value are comprehensively judged. Due to the addition of the evaluation information of the extracted content, the accuracy of the teacher course quality evaluation can be effectively improved.

[0059] In addition, the process of content analysis of video content by the content extractor includes: dividing the video content according to fixed preset unit time periods to obtain unit segments of each video; obtaining the pause time points, playback rate change curve over time and video heat curve in the historical playback data of each unit segment; calculating the key value of each unit segment according to the historical playback data, and obtaining the extracted content according to the size of the key value. Through the extraction process in the above technical solution, it is possible to accurately extract the key content in the teaching video based on the hot video content that users are concerned about and the relevant operation data (pause time points, playback rate change curve over time) in the teaching video watched by users. The accuracy of the extracted content can facilitate the teaching platform to manage the teaching content on the one hand, and on the other hand, it can also evaluate the quality of teachers' courses more comprehensively by obtaining evaluations separately.

[0060] It should be noted that the purpose of some of the analysis processes involved in the present invention is not only to carry out the evaluation process, but also to assist the teaching platform in managing the teaching video content.

[0061] In another embodiment, a key value calculation process is provided, which includes:

[0062] By formula:

[0063]

[0064] Calculate and obtain the key value Kv;

[0065] in, The starting time point for each unit segment, is the end time point of each unit segment, h(t) is the video heat curve, which is the curve of the number of video viewers changing with the video time bar, is the average heat value of the video, which is the average heat value of all unit segments The average value of The interval length of each unit segment. This parameter is selected and set by the platform personnel according to the accuracy requirements of the extraction. m is the number of segments of the playback rate over time curve in each unit segment, j=1, 2, ..., m; is the playback rate of the jth segment, is the duration of the jth segment, n is the number of pause time points in each unit segment, is the first tuning coefficient, is the second tuning parameter coefficient. The first tuning parameter coefficient and the second tuning parameter coefficient are both selected and set according to empirical data. Therefore, the obtained key value can be dynamically adjusted based on the user's attention and the user's unintentional usage habits. For example, when the user watches content that he thinks is important, the playback speed will be reduced or paused, which can further integrate the data of the user's usage process and improve the accuracy of the extracted content.

[0066] The process of obtaining the extracted content according to the size of the key value includes:

[0067] The key value Kv of each unit segment is compared with the preset fixed value K0, wherein the preset fixed value K0 is obtained by fitting based on empirical data. In this process, the extracted content is first divided manually, and then the critical value corresponding to the division time point is used as the fitting value. Through the simulation of multiple groups of data, the middle value of the multiple groups of data is selected as the preset fixed value K0, and the unit segment corresponding to the key value Kv>K0 is obtained as the extracted segment, and the adjacent extracted segments are merged as the extracted content. Through the above-mentioned content extraction process, the important parts of the teaching video can be segmented and extracted according to the size of the key value, which is convenient for the subsequent management of the teaching video and the individual evaluation process of each extracted content, thereby improving the accuracy of the quality assessment module in the teaching quality assessment.

[0068] In one embodiment, a process of analyzing a user's performance by a user performance analysis module is provided, which specifically includes: obtaining the performance of each node of the user, and drawing the performance of each node into a performance change curve; segmenting the user according to the initial performance of the user, and obtaining the user teaching effect value according to the deviation state of the user performance change curve in each segment relative to the overall performance change curve; assigning a teaching effect value to each teaching video according to the user's historical teaching video viewing data, and obtaining the teaching effect value assigned to each teaching video. Since in the prior art, the method of evaluating according to student performance is mainly based on the overall performance level of the user and the change status of the user performance, however, for users with different performance levels, the degree of change is obviously different. Therefore, in order to more accurately adjust the degree of change of the user performance, this embodiment divides the user according to the initial performance, and obtains the user teaching effect value according to the deviation state of the user performance change curve in each segment relative to the overall performance change curve, thereby achieving accurate evaluation of the user performance change, that is, evaluating the online course teaching quality by obtaining the user teaching effect value. In this process, the teaching effect value is assigned to each teaching video according to the user's historical teaching video viewing data, and the teaching effect value assigned to each teaching video is obtained, thereby achieving the process.

[0069] The process of calculating the user teaching effect value includes:

[0070] By formula:

[0071] Calculate and obtain the user teaching effect value E;

[0072] in, is the influence coefficient corresponding to the segment where the user's initial score is located. Different segments have different influence coefficients. The higher the level, the greater the corresponding influence coefficient. k is the k value of the user's score change curve. is the mean k value of all users’ performance change curves, so the formula The calculation process can judge the teaching results of a single user by obtaining the user teaching effect value E.

[0073] At the same time, the process of obtaining the teaching effect value of each teaching video includes:

[0074] By formula: Calculate the teaching effect value of each teaching video ;

[0075] Among them, Q is the number of users who watch each teaching video, y=1, 2, …, Q, is the teaching effect value of the yth user, The total viewing time of the user in this teaching video. is the total viewing time of the user in the corresponding type of video of the teaching video. Through the above calculation process, the teaching effect value can be calculated according to the different occupancy time of users in the same type of teaching videos. By making reasonable allocation, the teaching effect of each teaching video can be matched one-to-one with each user, which improves the accuracy of the teaching effect value in judging the teaching quality.

[0076] The present application also discloses a method for evaluating the quality of a teacher's course based on data analysis, which adopts the following technical solution: A method for evaluating the quality of a teacher's course based on data analysis, referring to the attached Figure 2 , including: collecting historical playback data of teaching videos through the playback data collection terminal; obtaining the evaluation information of the extracted content and the evaluation information of the entire teaching video in real time through the evaluation module; analyzing the user's performance through the user performance analysis module to obtain the teaching effect value of each teaching video; and evaluating the teaching quality according to the historical playback data of the teaching video, the evaluation information of the extracted content, the evaluation information of the entire teaching video and the teaching effect value through the quality evaluation module.

[0077] The quality assessment method in the present application realizes the extraction of key content in the teaching video content through the set content extractor, and at the same time, by separately obtaining the evaluation information of the extracted content, on the one hand, it is convenient to understand the user's knowledge point learning level in the management process of the education platform, and on the other hand, it realizes the accurate acquisition of the teacher's online course evaluation data, and then in the subsequent judgment process, improves the accuracy of the teacher's course quality assessment; in addition, the playback data acquisition end in this system is connected to the relevant playback data acquisition of the teaching video background, and when the evaluation module obtains the evaluation information, it will not only collect the evaluation information of the entire teaching video, but also obtain the evaluation information of the extracted content in real time after each extracted content is completed. Due to the addition of the evaluation information of the extracted content, the accuracy of the teacher's course quality assessment can be effectively improved.

[0078] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in the field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A teacher course quality evaluation system based on data analysis, characterized in that: include: Playback data collection terminal, used to collect historical playback data of teaching videos; A content extractor, used to perform content analysis on the video content according to the historical playback data, extract the video according to the content analysis result, and obtain the extracted content; An evaluation module, used to obtain evaluation information of the extracted content and the entire teaching video in real time; User performance analysis module, used to analyze the user's performance and obtain the teaching effect value of each teaching video; The quality assessment module is used to evaluate the teaching quality based on the historical playback data of the teaching video, the evaluation information of the extracted content, the evaluation information of the entire teaching video and the teaching effect value.

2. A teacher course quality evaluation system based on data analysis according to claim 1, characterized in that: The process of the content extractor performing content analysis on the video content includes: Divide the video content according to fixed preset unit time periods to obtain unit segments of each video; Obtain the pause time point, playback rate change curve over time and video heat curve in the historical playback data of each unit segment; The key value of each unit segment is calculated based on the historical playback data, and the extracted content is obtained based on the size of the key value.

3. A teacher course quality evaluation system based on data analysis according to claim 2, characterized in that: The calculation process of the key value includes: By formula: Calculate and obtain the key value Kv; in, The starting time point for each unit segment, is the end time point of each unit segment, h(t) is the video heat curve, is the average heat value of the video, The interval length of each unit segment, m is the number of segments of the playback rate versus time curve within each unit segment, j=1, 2, …, m; is the playback rate of the jth segment, is the duration of the jth segment, is the first tuning coefficient, is the second tuning parameter, and n is the number of pause time points in each unit segment.

4. A teacher course quality evaluation system based on data analysis according to claim 3, characterized in that: The process of obtaining the extracted content according to the size of the key value includes: The key value Kv of each unit segment is compared with the preset fixed value K0, and the unit segment corresponding to the key value Kv>K0 is obtained as the extraction segment, and the adjacent extraction segments are merged as the extraction content.

5. A teacher course quality evaluation system based on data analysis according to claim 4, characterized in that: The process of analyzing the user's performance by the user performance analysis module includes: Get the user's score at each node and plot the score of each node into a score change curve; The user's initial scores are divided into segments, and the user's teaching effect value is obtained according to the deviation state of the user's score change curve in each segment relative to the overall score change curve; A teaching effect value is assigned to each teaching video according to the user's historical teaching video viewing data to obtain the teaching effect value assigned to each teaching video.

6. A teacher course quality evaluation system based on data analysis according to claim 5, characterized in that: The process of calculating the user teaching effect value includes: By formula: Calculate and obtain the user teaching effect value E; in, is the influence coefficient corresponding to the segment where the user's initial score is located, k is the k value of the user's score change curve, is the mean k value of all users’ performance change curves.

7. A teacher course quality evaluation system based on data analysis according to claim 6, characterized in that: The process of obtaining the teaching effect value of each teaching video includes: By formula: Calculate the teaching effect value of each teaching video ; Among them, Q is the number of users who watch each teaching video, y=1, 2, …, Q, is the teaching effect value of the yth user, The total viewing time of the user in this teaching video. The total viewing time of the user for the corresponding type of videos in this teaching video.

8. A method for evaluating the quality of teacher courses based on data analysis, characterized in that: The method adopts a teacher course quality evaluation system based on data analysis as claimed in claim 1, comprising: Collect historical playback data of teaching videos through the playback data collection terminal; The evaluation module obtains the evaluation information of the extracted content and the evaluation information of the entire teaching video in real time; Analyze the user's performance through the user performance analysis module to obtain the teaching effect value of each teaching video; The teaching quality is evaluated through the quality assessment module based on the historical playback data of the teaching video, the evaluation information of the extracted content, the evaluation information of the entire teaching video and the teaching effect value.

Images